Minimax risk of matrix denoising by singular value thresholding

DOI10.1214/14-AOS1257zbMath1310.62014arXiv1304.2085MaRDI QIDQ482895

Matan Gavish, David L. Donoho

Publication date: 6 January 2015

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1304.2085

zbMATH Keywords

phase transitionnuclear norm minimizationmatrix denoisingmatrix completion from Gaussian measurementsmonotonicity of power functions of multivariate testsoptimal thresholdsingular value thresholdingStein unbiased risk estimate

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Minimax procedures in statistical decision theory (62C20) Semidefinite programming (90C22) Convex programming (90C25)

Related Items (36)

Heteroskedastic PCA: algorithm, optimality, and applications ⋮ On the non-asymptotic concentration of heteroskedastic Wishart-type matrix ⋮ A Schatten-\(q\) low-rank matrix perturbation analysis via perturbation projection error bound ⋮ Low Permutation-rank Matrices: Structural Properties and Noisy Completion ⋮ Adaptive shrinkage of singular values ⋮ Sharp MSE bounds for proximal denoising ⋮ Monte Carlo Simulation on the Stiefel Manifold via Polar Expansion ⋮ Singular vector and singular subspace distribution for the matrix denoising model ⋮ Multidimensional scaling of noisy high dimensional data ⋮ Optimal prediction in the linearly transformed spiked model ⋮ Optimal singular value shrinkage for operator norm loss: extending to non-square matrices ⋮ Optimal shrinkage of eigenvalues in the spiked covariance model ⋮ Statistical Inference, Learning and Models in Big Data ⋮ Double bias correction for high-dimensional sparse additive hazards regression with covariate measurement errors ⋮ Unnamed Item ⋮ A Zero-Inflated Logistic Normal Multinomial Model for Extracting Microbial Compositions ⋮ Testing in high-dimensional spiked models ⋮ Euclidean Representation of Low-Rank Matrices and Its Geometric Properties ⋮ Entrywise limit theorems for eigenvectors of signal-plus-noise matrix models with weak signals ⋮ A cross-validation framework for signal denoising with applications to trend filtering, dyadic CART and beyond ⋮ CGIHT: conjugate gradient iterative hard thresholding for compressed sensing and matrix completion ⋮ A singular value thresholding with diagonal-update algorithm for low-rank matrix completion ⋮ Minimax risk of matrix denoising by singular value thresholding ⋮ Normal approximation and confidence region of singular subspaces ⋮ Rate-optimal perturbation bounds for singular subspaces with applications to high-dimensional statistics ⋮ Matrix Denoising for Weighted Loss Functions and Heterogeneous Signals ⋮ Dynamic Mode Decomposition with Control ⋮ Research on a risk assessment method considering risk association ⋮ Conditions for equality in Anderson's theorem ⋮ Optimal estimation of Schatten norms of a rectangular matrix ⋮ Principal component analysis for zero-inflated compositional data ⋮ Bridging convex and nonconvex optimization in robust PCA: noise, outliers and missing data ⋮ Intelligent Initialization and Adaptive Thresholding for Iterative Matrix Completion: Some Statistical and Algorithmic Theory forAdaptive-Impute ⋮ Generalized SURE for optimal shrinkage of singular values in low-rank matrix denoising ⋮ Low-rank matrix denoising for count data using unbiased Kullback-Leibler risk estimation ⋮ Edge statistics of large dimensional deformed rectangular matrices

Uses Software

• CVX

Cites Work

• Unnamed Item
• Unnamed Item
• Reconstruction of a low-rank matrix in the presence of Gaussian noise
• Minimax risk of matrix denoising by singular value thresholding
• Estimation of high-dimensional low-rank matrices
• Null space conditions and thresholds for rank minimization
• Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
• Estimation of the mean of a multivariate normal distribution
• Minimax risk over \(l_ p\)-balls for \(l_ q\)-error
• Nonsmooth analysis of singular values. I: Theory
• Normalized Iterative Hard Thresholding for Matrix Completion
• The Optimal Hard Threshold for Singular Values is <inline-formula> <tex-math notation="TeX">\(4/\sqrt {3}\) </tex-math></inline-formula>
• Accurate Prediction of Phase Transitions in Compressed Sensing via a Connection to Minimax Denoising
• The Integral of a Symmetric Unimodal Function over a Symmetric Convex Set and Some Probability Inequalities
• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• Unbiased Risk Estimates for Singular Value Thresholding and Spectral Estimators
• The phase transition of matrix recovery from Gaussian measurements matches the minimax MSE of matrix denoising
• DISTRIBUTION OF EIGENVALUES FOR SOME SETS OF RANDOM MATRICES
• Monotonicity of the Power Functions of Some Tests of the Multivariate Linear Hypothesis

This page was built for publication: Minimax risk of matrix denoising by singular value thresholding